Abstract
Since first coined by Google in 2012, knowledge graph has received extensive attention from both industry and academia, and has been widely used in many scenarios with success, e.g. information retrieval, online recommendation, question-answering, and so on. However, traditional centralized construction of knowledge graph faces many challenges, such as laborious and time-consuming, vulnerable to manipulation or tampering, lacking scrutiny, among others. Therefore, in this paper, we propose a novel decentralized knowledge graph construction method by means of crowdsourcing, and the business logic of crowdsourcing is implemented by blockchain-powered smart contracts to guarantee the transparency, integrity, and auditability. On this basis, the decentralized knowledge graph is used for a deep recommender system, and case studies validate the effectiveness of the system. This paper is aimed at providing a novel decentralized approach for constructing knowledge graph and serving as reference and guidance for future research and practical applications of knowledge graph.
Highlights
As a directed labeled graph, knowledge graph encodes structured information of entities and their rich relations in a systematic way, and can better extract latent knowledge-level connections among objects
We propose a novel approach for decentralized construction of knowledge graphs based on blockchain-powered smart contracts, and the knowledge graph is used as inputs to the deep neural network to complete the recommendation task
WORK In this paper, we propose a novel decentralized knowledge graph construction approach based on blockchain-powered smart contracts, the knowledge graph is used for a deep recommender system, and case studies validate the effectiveness of the system
Summary
As a directed labeled graph, knowledge graph encodes structured information of entities and their rich relations in a systematic way, and can better extract latent knowledge-level connections among objects. We propose a novel approach for decentralized construction of knowledge graphs based on blockchain-powered smart contracts, and the knowledge graph is used as inputs to the deep neural network to complete the recommendation task. As for the Off-Chain part, the knowledge graph embedding is utilized to formulate the low-dimensional representation vector for the entities and relations of the Updated Graph, and a deep neural network is adopted to carry out the recommendation (In this study, our aim is to recommend suitable employees for a new work task). After the training is completed, we can obtain the vector representation of entities and relations for a given knowledge graph
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
